Catalunya 2022

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds useful context beyond annotations by specifying the exact output shape (hierarchy with canonical slugs) and the document contents, which help an agent predict behavior without exceeding annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense sentence. It includes the document name, structure counts, creator details, and navigation hint without any wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only metadata tool with one optional parameter and no output schema, the description completely covers the return value (hierarchy with slugs) and the intended navigation path. No critical information is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% coverage for the single locale parameter, including enum values and defaults. The description adds no parameter-specific nuance, so the baseline of 3 applies since the schema fully handles parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get', the specific resource (the policy document with its full name), and what it returns (the hierarchy with 3 spheres, 12 goals, 91 actions). It also distinguishes itself from the sibling tool get_section by noting that the output is for navigation via that tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates that this tool returns the complete structure and that navigation proceeds via get_section, giving a clear usage context. However, it does not explicitly contrast with list_proposals or search_document, so exclusions are implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, providing the safety profile. The description adds valuable context about slug patterns and static pages, and implies a closed universe (openWorldHint false) with specific valid slugs. It doesn't cover error behavior or return format, but given the simplicity and annotation coverage, this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, each contributing distinct value: purpose, slug patterns, and static pages with a pointer to metadata. No redundant wording or fluff. Front-loaded with the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool, the description is complete: it explains what is returned, how to construct valid slugs, and where to find other slugs. There is no output schema, but 'full text' adequately describes the return. The inclusion of static pages and locale details (via schema) rounds out the picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both parameters documented. The slug parameter gets enhanced meaning through the description's pattern examples and static page list, which goes beyond the bare schema description. The locale parameter is fully self-explanatory with enum and default, so the description adds no extra but doesn't need to.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves the full text of a section via canonical slug. It includes specific slug patterns and lists static pages, which distinguishes it from siblings like get_document_metadata and search_document. The verb 'retrieve' is precise and matches the read-only nature.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly points to get_document_metadata for discovering slugs, offering a clear alternative for that use case. It doesn't explicitly state when not to use this tool or mention other siblings, but the context makes the primary usage clear. This is solid guidance but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only and idempotent behavior; the description adds useful context: the exact number of proposals (91), which fields are returned, and that filters are optional. It does not contradict annotations. It could add more about default locale behavior, but the schema covers locale, so this is acceptable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: the first states the tool's purpose and filtering options; the second lists the return fields and the recommended follow-up tool. No redundant information, front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list tool with three optional params and no output schema, the description covers scope, filters, return fields, and the next step (get_section). It is complete enough for an agent to invoke correctly without additional documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with goalId, sphereId, and locale all explained. The description only restates the filter ranges (sphere 1-3, goal 1-12) and does not add new parameter semantics beyond what the schema provides. Baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists all 91 action proposals from the Catalunya 2022 document, with optional filtering by sphere or goal. It distinguishes itself from siblings by specifying the returned fields (actionId, goalId, sphereId, title, slug, url) and by pointing to get_section for full content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides a concrete usage direction: use list_proposals to get slugs, then use get_section to read full action content. This implies a two-step workflow and helps the agent decide when to use this tool, though it doesn't explicitly mention when to prefer search_document or get_document_metadata.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, non-destructive. The description adds concrete behaviors: returns max 10 results, includes canonical slugs and text snippets, and normalizes diacritics (e.g., 'educacio' matches 'educació'). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the action. Each sentence adds value: purpose, result format, and search behavior. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool without output schema, the description adequately describes result shape (up to 10 results, slugs, snippets), search behavior (diacritics), and linkage to get_section. Combined with rich schema and annotations, it covers the essential context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters are fully described in the schema (100% coverage). The description does not add new parameter details, but the diacritics example reinforces query behavior. Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Search the Catalunya 2022 - RESET policy document by keyword' with a specific verb and resource. The return of canonical slugs for get_section differentiates it from sibling tools that retrieve specific sections or list proposals.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Mentions follow-up with get_section and describes the search context. It implies usage for keyword discovery vs. direct lookup, and the diacritics example gives practical search guidance. Lacks explicit when-not-to-use or alternatives, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.